© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 13454
    Prev
    Next
    INDEX
    Explanations

    terms related to concepts, opinions, and statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to lack and overlap in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igmatic
    -0.71
     amnesty
    -0.69
    zie
    -0.62
    dit
    -0.61
    ze
    -0.61
    NAS
    -0.59
    uther
    -0.58
    geries
    -0.56
    TRY
    -0.56
     consult
    -0.55
    POSITIVE LOGITS
     mattered
    0.78
     exceeds
    0.74
     exceeded
    0.72
     coupled
    0.69
     prompted
    0.69
     proved
    0.68
     alone
    0.68
    angers
    0.67
     outweigh
    0.66
    eness
    0.65
    Activations Density 0.539%

    No Known Activations